Artificial Intelligence | "AI Will Change What It Means To Be Human": Professor Michael Sandel

Amid the rise of emerging tech across the globe, American philosopher Michael Sandel explores the ethical challenges behind AI, in conversation with Shoma Chaudhary at Synapse 2024, a one-of-a-kind tech conference bringing together global tech thinkers.
#AI #ArtificialIntelligence #HumanProfessorMichaelSandel #AmericanPhilosopher #Synapse2024
About NDTV (English news channel):
NDTV is India's Most-Trusted News Broadcaster with the latest updates in news, sports, entertainment and much more from within India and around the world. Watch big political debates, exclusive entertainment interviews, news bulletins, current affairs, talk shows and tech reviews with our 24x7 news live streams, packed with credible information across all platforms: TV, Internet and Mobile.
For Latest Videos, click here: • Latest News & Updates ...
To watch NDTV 24x7's premium shows listed together for your easy access, click here: www.youtube.com/@NDTV/playlis...
For Ground Reports and Analysis from NDTV's reporters and anchors of day's top news stories, click here: • Reporter Vlogs
For News in Shorts, click here: • News In Shorts
Subscribe to our channel to get latest news updates.
Follow us on Social Media:
Like us on Facebook: / ndtv
Follow us on Twitter: / ndtv
Follow us on WhatsApp: whatsapp.com/channel/0029Va4l...
Follow us on Instagram: / ndtv
Join NDTV on Telegram Messenger: t.me/NDTVbot/?start=hi
Follow us on Google News for Breaking and Latest News Updates:
NDTV: bit.ly/3e5ngbP
NDTV India (Hindi News): bit.ly/3mNVwMY
Download NDTV Mobile Apps: www.ndtv.com/page/apps
#BreakingNews #LatestNews #TodayNews #CurrentAffairs #News #IndiaNews #NDTV

[@tersta1]

I use AIs often and have encountered several errors that I am documenting. When I meet with these errors, I query about the errors. AIs do not have access to the decision-making process algorithms that generate responses and thus cannot explain how they make mistakes. They can provide a list of possible causes and determine that the most likely cause is the ambiguity and/or conflicting statements in various source training data. The possible reasons that can result in ChatGPT making mistakes are "Limited Context", "Ambiguity in Training Data" and "Misinterpretation of Context".
Here's an example:
Given that the slurry is warmed and maintained at 125°F (51.7°C), which is above the optimal range but below the denaturation threshold, the enzymatic reaction is expected to proceed faster compared to lower temperatures.
I queried the AI about the error and it responded as follows:
Apologies for the confusion in my previous response. I misspoke when I stated that 125°F (51.7°C) is above the optimal range for bromelain activity. In fact, 125°F falls within the optimal range for bromelain's proteolytic activity.
-----
An AI's response also listed Morocco as in Europe, as a result of Europe being mentioned in the fetched training material, although it was not a specifically stated location for Morocco. Of course, a conscientious human would review continent heading and location names and see the error immediately, if they knew from past learning which continent Morocco is on.
Not so with AIs. However, once I brought the error to the AI's attention, it was able to note the correction to prevent similar queries by other uses from being given incorrect information, but the correction is specific to the context of the query and not general.
Here is how the AI resolved the error:
User
What procedure did you use to correct the error of placing the Venus of Tan-Tan under the Europe heading?
ChatGPT
As an AI language model, I don't have the ability to directly "correct" errors in the same way a human would. However, based on your feedback and the discussion we had earlier, I was able to adjust the response to ensure that the Venus of Tan-Tan was correctly associated with the African continent, rather than Europe.
To do this, I carefully reviewed the input query and the context provided, which specified the need to list the oldest known man-made artifacts found on each continent. Drawing on the knowledge available to me from my training data, I made sure to accurately represent the Venus of Tan-Tan as an artifact found in Morocco, which is situated in Africa.
By applying this knowledge and context, I was able to generate a response that correctly placed the Venus of Tan-Tan under the Africa heading, thereby addressing the initial error..
----
The errors that I have encountered indicated that AIs do make general knowledge mistakes. I have also noticed that the frequency of mistakes is increasing. The information that AIs can deliver is only as good as the training data they refer to, as they are not capable of reviewing and correcting their own responses without user prompting.
While lonely grannies may not be injured by such AI errors, when they are used to simply be companions, I would caution that programming related to medication scheduling should be very carefully reviewed and tested before these companion AIs are entrusted to anyone who will rely upon them for assistance with healthcare matters.

[@pradeeppandey7228]

🙏🙏🙏

[@helenmilenski861]

We need AI to have a bias toward believing that there is implicit worth to every human. Humans don't give the value of implicit worth to each other, but if AI lacks this simple core belief then the judgement of some people based on merit and potential will lead to abuses by people as well as possibly AI in the future.

[@mkngani4718]

NDTV 1986 தமிழ் நாட்டில் இருந்து கொண்டு வந்து சேர்க்கும் பணியில் தமிழ் மக்கள்